Se agrego gitignore y se modifico segun recomendaciones el app.yp

.gitignore

@@ -0,0 +1 @@
+.vscode

app.py

@@ -1,63 +1,47 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("jhangmez/CHATPRG-v0.2.1-Meta-Llama-3.1-8B-bnb-4bit-q4_k_m")
 
+def format_message(role, content):
+    return f"<|im_start|>{role} {content}<|im_end|> "
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    formatted_messages = [format_message("system", system_message)]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    for human, assistant in history:
+        if human:
+            formatted_messages.append(format_message("user", human))
+        if assistant:
+            formatted_messages.append(format_message("assistant", assistant))
 
-    messages.append({"role": "user", "content": message})
+    formatted_messages.append(format_message("user", message))
+    formatted_messages.append("<|im_start|>assistant ")
 
-    response = ""
+    full_prompt = "".join(formatted_messages)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    response = ""
+    for chunk in client.text_generation(
+        full_prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        response += chunk
+        yield response.strip()
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
+    title="Meta Llama 3.1 8B Chatbot",
+    description="A chatbot powered by Meta Llama 3.1 8B model."
 )
 
-
 if __name__ == "__main__":
     demo.launch()